PinnedInTowards AIbyBurak Degirmencioglu·Nov 13, 2025The Secret Behind Fast LLM Inference: Unlocking the KV CacheWhat is the KV Cache? The Secret to Fast LLM Inference. Learn what the KV Cache is and modern optimization techniques.
PinnedInTowards AIbyBurak Degirmencioglu·Aug 27, 2025The Next Step in Agentic AI: Context Engineering?Our interactions with artificial intelligence have become much more complex and dynamic than simply giving commands. We now expect them not…
InData Science CollectivebyBurak Degirmencioglu·Dec 4, 2025Architecting Human-in-the-Loop Agents: Interrupts, Persistence, and State Management in LangGraphMaster Human-in-the-Loop to build autonomous agents. Implement dynamic interrupts, persistence, memory, and streaming. Read the full guide!
InData Science CollectivebyBurak Degirmencioglu·Dec 1, 2025RAG Architectures: A Complete Guide for 2025What is Retrieval Augmented Generation? Stop LLM hallucinations. Master RAG with our guide from HyDe to Agentic RAG. Read the full guideA response icon2A response icon2
InTowards AIbyBurak Degirmencioglu·Nov 24, 2025Architecting Autonomy: A Technical Framework for Agentic AI SystemsMaster Agentic Architectures, ReAct & multi-agent swarms to build autonomous AI systems. Optimize reasoning & cost.
InTowards AIbyBurak Degirmencioglu·Nov 20, 2025The Engineering Guide to Efficient LLM Inference: Metrics, Memory, and MathematicsHigh latency stalling your AI? Master LLM inference optimization. Balance throughput, memory & GPU metrics effectively. Boost your model!
InTowards AIbyBurak Degirmencioglu·Nov 18, 2025Mastering Continual Pretraining: How to Transform Generalist LLMs into Domain ExpertsLearn Continual Pretraining (CPT) to turn generalist LLMs into domain experts. Deep dive the differences between CPT and Fine-Tuning.
InArtificial Intelligence in Plain EnglishbyBurak Degirmencioglu·Nov 16, 2025Advanced Quantization Techniques: The Ultimate Guide to Unlocking LLM PotentialA deep dive into Advanced Quantization for LLMs. Learn the trade-offs of PTQ vs. QAT and master techniques like SmoothQuant, GPTQ, and AWQ.
InTowards AIbyBurak Degirmencioglu·Nov 7, 2025Quantization: How to Accelerate Big AI ModelsLarge Language Model(LLM) Quantization: A Complete Guide to PTQ, QAT & Tools
InTowards AIbyBurak Degirmencioglu·Nov 4, 2025Beyond Scarcity: How LLM-Driven Synthetic Data Generation is Reshaping AISynthetic Data Generation: How LLMs Solve AI’s Data Bottleneck